Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Proebsting, Grace, Poliak, Adam
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916433803345920
author Proebsting, Grace
Poliak, Adam
author_facet Proebsting, Grace
Poliak, Adam
contents We test whether replacing crowdsource workers with LLMs to write Natural Language Inference (NLI) hypotheses similarly results in annotation artifacts. We recreate a portion of the Stanford NLI corpus using GPT-4, Llama-2 and Mistral 7b, and train hypothesis-only classifiers to determine whether LLM-elicited hypotheses contain annotation artifacts. On our LLM-elicited NLI datasets, BERT-based hypothesis-only classifiers achieve between 86-96% accuracy, indicating these datasets contain hypothesis-only artifacts. We also find frequent "give-aways" in LLM-generated hypotheses, e.g. the phrase "swimming in a pool" appears in more than 10,000 contradictions generated by GPT-4. Our analysis provides empirical evidence that well-attested biases in NLI can persist in LLM-generated data.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08996
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference
Proebsting, Grace
Poliak, Adam
Computation and Language
We test whether replacing crowdsource workers with LLMs to write Natural Language Inference (NLI) hypotheses similarly results in annotation artifacts. We recreate a portion of the Stanford NLI corpus using GPT-4, Llama-2 and Mistral 7b, and train hypothesis-only classifiers to determine whether LLM-elicited hypotheses contain annotation artifacts. On our LLM-elicited NLI datasets, BERT-based hypothesis-only classifiers achieve between 86-96% accuracy, indicating these datasets contain hypothesis-only artifacts. We also find frequent "give-aways" in LLM-generated hypotheses, e.g. the phrase "swimming in a pool" appears in more than 10,000 contradictions generated by GPT-4. Our analysis provides empirical evidence that well-attested biases in NLI can persist in LLM-generated data.
title Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference
topic Computation and Language
url https://arxiv.org/abs/2410.08996